Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures

TL;DR

This paper presents CUDA autotuning benchmarks and a framework for evaluating search algorithms using hardware performance counters across various GPU architectures, facilitating research in GPU code optimization.

Contribution

It introduces a set of CUDA benchmarks, a data-driven evaluation framework, and models for predicting performance counters from tuning parameters, aiding GPU autotuning research.

Findings

Collected hardware performance data for five CUDA benchmarks on multiple GPUs.

Developed scripts for robust evaluation and comparison of tuning search algorithms.

Created models to predict performance counters from tuning parameters.

Abstract

We have developed several autotuning benchmarks in CUDA that take into account performance-relevant source-code parameters and reach near peak-performance on various GPU architectures. We have used them during the development and evaluation of a novel search method for tuning space proposed in [1]. With our framework Kernel Tuning Toolkit, freely available at Github, we measured computation times and hardware performance counters on several GPUs for the complete tuning spaces of five benchmarks. These data, which we provide here, might benefit research of search algorithms for the tuning spaces of GPU codes or research of relation between applied code optimization, hardware performance counters, and GPU kernels' performance. Moreover, we describe the scripts we used for robust evaluation of our searcher and comparison to others in detail. In particular, the script that simulates the tuning, i.e., replaces time-demanding compiling and executing the tuned kernels with a quick reading of the computation time from our measured data, makes it possible to inspect the convergence of tuning search over a large number of experiments. These scripts, freely available with our other codes, make it easier to experiment with search algorithms and compare them in a robust way. During our research, we generated models for predicting values of performance counters from values of tuning parameters of our benchmarks. Here, we provide the models themselves and describe the scripts we implemented for their training. These data might benefit researchers who want to reproduce or build on our research.